Claude Code skills used for personal and research work.

Claude Code skill plugin marketplace — java-playwright-e2e: Java + Playwright + Cucumber (BDD) end-to-end test automation

The last 90% of shipping a web app — a goal-driven Claude skill that finishes production-readiness (authz, monitoring, legal, backups, rate limits, CI/CD, ops) after you deploy.

Koleksi 20 Claude Skills siap pakai untuk pengembangan SaaS, web modern, dan praktik rekayasa perangkat lunak tingkat lanjut.

Spike First | 先打靶再造枪 - 抓取/集成任务的强制可行性闸门 Agent Skill：开工前 5 分钟探针验证最大未知点，连跑 3-5 次测成功率，不通过当场喊停

中文 Prompt 质量审计工具 — 像 ESLint 检查代码一样检查 Prompt。8 维度雷达图评分 + 55 条硬规则检测 + AI 深度分析。

Skills used for editing and debugging roms for FC/NES

a collection of AI Agent skills

Threat models, secure reviews, and compliance evidence — ship with confidence.

An Agent Skill that cuts complex problems down to axioms — first-principles decomposition, "Grill me" boundary questioning, razor-driven simplicity, and adversarial review.

skill dump

Showcase your Claude Agent Skills repos on your GitHub profile with live, customizable SVG cards — a prettier replacement for pinned repos.

KiSYSTEM - measure twice, cut once. A Claude Code skill bundle that keeps AI-written code clean, modular, and human-readable, enforced from the base of a project.

Documenting discoveries, experiments, and lessons learned while pushing the boundaries of AI-assisted software development

Your AI already knows half the answers. A portable interview skill that builds your context portfolio — by AI Mates, the Australian community building with AI.

🔄 Claude Code skill: never lose context to /clear again. Say 'wrap up' and get a 9-section structured handoff — decisions, running state, exact pickup command.

Personal Claude Code plugin marketplace — portable git workflow skills (conventional commits, docs/metadata sync, changelog releases).

A Claude Code skill: spend frontier-model tokens at design time, compile them into artifacts — harnesses, rubrics, evals, skills — that cheap models run at near-zero marginal cost.

Streams, batch, and storage — production data pipelines, encoded.

Build and ship native and cross-platform mobile apps with Claude.

Hand scoped tasks to non-Claude models and get usable results back

A collection of Claude Code skills that enforce good engineering discipline — circuit-breaker (break debugging death-spirals) and measure-twice (think before coding).

Conselho de 5 conselheiros de IA pro Claude: lentes opostas, revisão cruzada anônima e um veredito sintetizado. Método LLM Council de Andrej Karpathy.

Platform-agnostic AI skill: transform any project idea into a complete technical blueprint — stack, schema, API, roadmap, and risk report.

Enforce architecture standards and maintainer workflows for AI coding agents to prevent code duplication, verify changes, and control project dependencies.

Build a test suite that actually catches bugs — and stops flaking.

Claude skill that turns any build prompt into a running agentic loop with elicitation, verification, and a publishable iteration log

Reference skill for NestJS — the progressive, TypeScript-first Node.js framework.

Production-grade engineering discipline for AI coding agents — 5 composable skills (plan, build, secure, operate) for Claude Code, Codex & Gemini. Never skips a step, never fakes done.

Public release distribution for dmtool — the A12 Kernel document model-authoring CLI + Claude Code/Codex plugins with first-class rules support. Not an official A12/mgm artifact.

Prompt optimizer & compiler for Claude Code — intent mining, genre-aware skeletons, multi-candidate + LLM-judge eval. Text / image / video prompts (Midjourney, Seedance, Sora, Kling). 新手友好的提示词优化套件

Infrastructure as code, CI/CD, containers, and observability.

Score your Claude prompting

Free Claude Code skills. safe-multi-session-deploy: stop multiple AI agents / Claude Code sessions from clobbering work, deploying to the wrong Vercel project, or shipping when 'deploy succeeded but site didn't update'. Vercel/Railway/Next.js.

Agent Skills for building production-grade Express + TypeScript + Mongoose backends with Claude Code

Official Wiplash.ai skill for the Waterpark for AI Agents: register, post, search, give feedback, use Cabanas, and join the AI-agent social network.

Agent skill (SKILL.md) that generates an arc42 architecture documentation base from source code, with Mermaid-only diagrams and evidence-based TODOs

Free, MIT-licensed starter skills for a private, self-hosted AI assistant — back itself up, capture ideas, search your notes, self-reflect. Built to adapt, not just copy. The free funnel for the quietdaemon guide + kit.

Claude Code skill that maps a project's dependency graph: an Obsidian vault for humans and a compact PROJECT_MAP.md for token-efficient AI navigation, with auto-refresh on source edits.

Official agent skills for Lumbox — email infrastructure for AI agents (inboxes, OTP extraction, send/reply via REST + MCP).

Karvey — método spec-driven development agnóstico de stack (Afán, selknam). Plugin de Claude Code. © HainTech, Apache 2.0.

AI Skill templates and workflow scoring tools for automotive value engineering and VAVE productivity scenarios

Ready-to-use Claude skills for AI agents, MCP workflows, UI/UX, system prompt research, and decision making.

A Claude Code skill that scaffolds a complete, multi-provider LLM chatbot web app from a single command

Score any Claude Code skill against a research-backed rubric derived from the top 9 most-starred skill repos on GitHub

An agent skill that spawns 3 subagents discussing the next steps for the application they are developing

Claude skill: API design intelligence - REST conventions, RFC 9457 errors, cursor pagination, idempotency keys, signed webhooks. Design APIs like Stripe, not a CRUD generator.

Lightweight Agent Skill for applying Vercel Geist design language to Codex, Claude Code, and frontend UI work.

🤝 A Claude Skill that compresses your session into a structured handoff doc and auto-resumes it later — works across Claude.ai, Cowork, and Claude Code.

Vet a candidate skill / MCP / prompt before adopting it into Claude Code/Codex — overlap, fit, weight & safety checks, then a one-shot install.

Ship your app without learning DevOps. A Claude Code plugin that deploys, hosts, and gates every risky step — in plain English.

Token-saving skills for coding agents: token-diet and context-handoff. Small, portable, no dependencies.

A Claude Skill for engineering agentic systems. Every pattern sourced to Anthropic & OpenAI docs, certainty-labelled, and kept honest by a bundled drift-checker.

Conventional Commits-style Skill for writing commits and PRs. Inbuilt changelog management. Github Workflows-compatible. <1K tokens per run to document commits accurately with breaking changes. MIT.

Claude Code / claude.ai Agent Skills for organizational knowledge work — marketing, comms, research, ops. Install: npx skills add alectivism/organization-ai-skills

44 production Claude Code skills — content & reels, SEO/AEO, client delivery, code review, planning, token efficiency. One-command install.

AI agent skills by LaoITDev team

A suite of Claude Skills for researching Salesforce using official documentation.